SANN Overviews - Predicting Future Data and Deployment
A fully trained neural network can be used for making predictions on any future data with variables that are thought to have been generated by the same underlying relations and processes as the original set used to train the model. The ability to generalize is an important feature of neural networks, and the process of using neural networks for making predictions in the future is known as deployment. STATISTICA Automated Neural Networks generated models can be saved and re-deployed later using the Predictive Markup Model Language (PMML), C/C++, and SAS.
There is one issue that needs to be considered, however, when deploying neural network models. One should not attempt to extrapolate, i.e., one should not present the neural network model with input values that differ significantly from those used to train the network. This is known as extrapolation, which is generally unwise and unsafe.